CVE-2026-105697

CRITICALPre-NVD 9.99.9—
EchelonGraph scoreMEDIUM confidence

This critical-severity CVE scores 9.9 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.4% (31st percentile of EPSS-scored CVEs). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
Trending — 3 sources updated this week
9.9EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.4%CVSS: 9.9Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to reach the MCP server settings ("Settings → MCP Servers → Add MCP Server", POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a "server" whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow) — even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3.

CVSS v3
9.9
EG Score
9.9CRITICALmedium confidence
EG Risk
45
EG Risk 45/100CISA SSVC

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity99% × 45%
Exploitation0% × 40%
Automatability0% × 15%
CISA SSVC: Track at low or medium mission impact; Track* at high (mission-essential systems).
Action: A fix is available. Apply it within your standard update timelines.
EPSS PROB
0.4%
EPSS %ILE
31st
KEV
Not listed

CISA SSVCTrack at low or medium mission impact; Track* at high (mission-essential systems).

A fix is available. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). Mission impact is CISA's Mission & Well-being decision point, and only you can judge it: high means the affected system is essential to your organisation's mission, or its compromise could cause irreversible harm to people. CISA's decision table

Published

October 5, 2026

Last Modified

October 6, 2026

Advisory Details (6)

Auto-updated Oct 6, 2026
🔬 Proof of concept available. Patch available. Sources: github_commit, github_pr, github_release, github.
githubMentions a patch (unverified)🟡 PoC Available

Langflow < 1.10.3: OS command injection (RCE) via arbitrary command in MCP stdio server configuration · Advisory · langflow-ai/langflow · GitHub

https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45
github_release Patch Available

1.10.3

Patch available: langflow-ai/langflow v1.10.3

https://github.com/langflow-ai/langflow/releases/tag/v1.10.3
github_pr

fix(security): harden MCP stdio configuration

Fix merged in langflow-ai/langflow PR #14036 on 2026-07-14 — awaiting tagged release

https://github.com/langflow-ai/langflow/pull/14036
github_pr

fix: prevent MCP command injection via allowlist validation (CWE-78)

Fix merged in langflow-ai/langflow PR #12290 on 2026-03-27 — awaiting tagged release

https://github.com/langflow-ai/langflow/pull/12290
github_commit

commit efbc4a16e639 (langflow-ai/langflow)

Fix landed in langflow-ai/langflow commit efbc4a16e639 — awaiting tagged release

https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0
github_commit

commit eba285edf1dd (langflow-ai/langflow)

Fix landed in langflow-ai/langflow commit eba285edf1dd — awaiting tagged release

https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d

Vendor Advisories for CVE-2026-105697(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 6× in last 7d / 6× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-10-06 15:23 UTCEG score recompute
  2. 2026-10-06 15:17 UTCEPSS rescore
  3. 2026-10-06 14:55 UTCEG score recompute
  4. 2026-10-05 21:23 UTCEG score recompute
  5. 2026-10-05 21:09 UTCEG score recompute
  6. 2026-10-05 21:05 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-105697?
CVE-2026-105697 is a critical vulnerability published on October 5, 2026. Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to…
When was CVE-2026-105697 disclosed?
CVE-2026-105697 was first published on October 5, 2026, with the most recent update on October 6, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-105697 actively exploited?
CVE-2026-105697 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (31st percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-105697?
CVE-2026-105697 has a CVSS base score of 9.9 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-105697?
A fix for CVE-2026-105697 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-105697 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-105697

Explore →

Is Your Infrastructure Affected by CVE-2026-105697?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs